Optimisation and Parallelism in Synchronous Digital Circuit Simulators

Digital circuit simulation often requires a large amount of computation, resulting in long run times. We consider several techniques for optimising a brute force synchronous circuit simulator: an algorithm using an event queue that avoids recalculating quiescent parts of the circuit, a marking algorithm that is similar to the event queue but that avoids a central data structure, and a lazy algorithm that avoids calculating signals whose values are not needed. Two target architectures for the simulator are used: a sequential CPU, and a parallel GPGPU. The interactions between the different optimisations are discussed, and the performance is measured while the algorithms are simulating a simple but realistic scalable circuit.